Search Results (1,680)

Optimizing nutrient management in organic polytunnel production remains challenging due to the limited availability of field-based knowledge on the mineralization dynamics of organic fertilizers. At the same time, microalgae-based products such as Chlorella vulgaris have gained increasing attention in recent research, yet their interactions with nutrient supply intensity are not well understood. This study aimed to evaluate the effects of increasing nutrient supply intensities (34, 116, and 189 kg ha⁻¹ N from different organic sources), in combination with C. vulgaris foliar application, on the crop performance of kapia pepper and a subsequent leafy green crop under on-farm organic polytunnel conditions on soil with moderate organic matter content. Increasing production intensity did not result in significant improvements in pepper yield or vegetative biomass (p > 0.05), and no significant residual effects of nutrient supply were detected in the yield of the subsequent leafy green crop (p: 0.08–0.94). C. vulgaris treatment showed predominantly non-significant but positive trends in several parameters, but only in combination with high-intensity technology, while reducing the total pest damage of the thrips and stinkbug index up to 15.7% in most technology variations. These results indicate that the effects of C. vulgaris may be strongly context-dependent and confirm that increasing the intensity of nutrient supply may carry the risks of conventionalization of organic farming practices. Full article

As food security gains increasing attention, automated pest monitoring is crucial for agricultural early warning systems. However, in practical light-trap capturing sensors, the extremely small scale of pests and complex background interference, such as unexpected reflection and occlusions, severely undermine the performance of existing models, resulting in frequent missed and false detections. To deal with these challenges, this study proposes EP-YOLO, an enhanced lightweight detection architecture based on YOLOv8n. Specifically, to retain the spatial pixels of micro-targets during downsampling and isolate pest features while eliminating background noise without compromising channel information, the Spatial-to-Depth Convolution (SPD) module and the Efficient Multi-Scale Attention (EMA) module are introduced. We evaluate our model through experiments on Pest24, a dataset consisting of 24 tiny pest categories. The results demonstrate that EP-YOLO achieves a mAP@50 and mAP@50:95 of 70.5% and 47.3%, respectively, improving upon the baseline by 1.1% and 1.9%. Furthermore, EP-YOLO achieves a significant improvement in detecting certain extremely small pests. For example, Rice planthopper and Plutella xylostella show improvements of 8.4% and 3.1%, respectively, compared to the baseline. In conclusion, the physical limitations of detecting tiny pests are successfully overcome by EP-YOLO, providing a robust and deployable design for real-time agricultural monitoring systems. Full article

Galeruca daurica (Joannis) (Coleoptera: Chrysomelidae) is an oligophagous pest in which both adults and larvae prefer to feed on Allium forage grasses of the Liliaceae family. In this study, we identified gustatory receptor (GR) genes based on the transcriptome data of G. daurica; analyzed the expression profiles of these GR genes across different larval instars and various tissues of male and female adults using quantitative real-time PCR (qRT-PCR); detected the electrophysiological responses of the mouthparts of male and female G. daurica adults to flavonoids and carbohydrates using single sensillum recording (SSR); and recorded the changes in food consumption of G. daurica adults after feeding on six host plant-derived metabolites. A total of 26 GR genes were identified from the transcriptome data of adult and larval of G. daurica. Phylogenetic analysis was performed to screen candidate functional gustatory receptor genes, including four sugar receptors (GdauGR7, GdauGR10, GdauGR14 and GdauGR28), seven bitter receptors (GdauGR11, GdauGR16~17, GdauGR22, GdauGR25~26 and GdauGR30), and two CO₂ receptors (GdauGR15 and GdauGR20). Larval expression profiling of GdauGRs in G. daurica revealed that the relative expression levels of 17 genes exhibited dynamic changes during larval growth and development. GdauGRs were expressed to varying degrees in the antennae, mouthparts, brain, gut, and forelegs of adult G. daurica, with sex-specific differences. Notably, the expression levels of GdauGR4, GdauGR9 and GdauGR16 in the gut were extremely significantly higher than those in other tissues. In the SSR test, the six tested flavonoids and one carbohydrate were able to induce robust electrophysiological responses in the gustatory sensilla on the antennae and mouthparts of adult G. daurica at specific concentrations. In addition, the supplementation of several host-derived metabolites altered the food consumption of adult G. daurica. These findings lay a solid foundation for elucidating the molecular mechanisms underlying gustatory recognition and host adaptation in G. daurica. Full article

Identifying pest infestations in fresh fruits is a crucial aspect of international trade. Currently, inspections rely on visual observations and destructive sampling, which are, in most cases, quite demanding. The detection of oviposition signs or early larval development is largely not feasible. Therefore, new methods that are sensitive and non-destructive are urgently needed to detect fruit fly infestation during inspections of fresh produce before their introduction and spread into pest-free areas. Portable electronic olfactory systems, or electronic noses (e-noses), are used in various scientific fields and industries. In this study, we evaluated the potential of a portable PEN3 electronic nose to discriminate between non-infested and infested fruits for three fruit fly species: Ceratitis capitata (Wiedemann), Bactrocera dorsalis (Hendel), and Bactrocera zonata (Saunders) (Diptera: Tephritidae). E-nose datasets were generated from samples of each combination of fruit, fruit fly species, infestation status, and storage condition. These datasets were used to develop classification models. The classification accuracy of the models ranged from 50 to 99% during calibration and cross-validation conditions. However, their performance decreased substantially when applied to independent datasets, highlighting limitations in robustness. These findings indicate that although the PEN3 system shows promise as a non-destructive detection tool, its performance is strongly influenced by seasonal and experimental variability. Further work is needed to incorporate multi-season and multi-variety datasets, improve calibration, and robust validation before practical implementation in field inspection systems. Full article

Aimed at the practical challenge that pest occurrence in fruit and vegetable horticultural production exhibits strong environmental dependency, pronounced stage characteristics, and high sensitivity to control decision-making, a multimodal pest recognition and occurrence risk joint modeling method is proposed to address the limitation that conventional intelligent plant protection systems focus primarily on pest identification while lacking risk discrimination capability. Within a unified network framework, pest visual information and environmental temporal data are integrated through the construction of an environment-guided representation learning mechanism, a recognition–risk joint optimization strategy, and a risk-aware decision representation modeling structure. In this manner, pest category recognition and occurrence risk evaluation are conducted simultaneously, thereby providing direct decision support for precision prevention and control in fruit and vegetable production. Systematic experimental evaluation is conducted based on multi-crop and multi-year field data collected from Wuyuan County, Bayannur City, Inner Mongolia. Overall comparative results demonstrate that an identification accuracy of $0.947$, a precision of $0.936$, and a recall of $0.924$ are achieved on the test set, all of which significantly outperform mainstream visual detection models such as YOLOv8, DETR, and Mask R-CNN. In terms of detection performance, mAP@50 and mAP@75 reach $0.962$ and $0.821$, respectively, indicating stable localization and discrimination capability under complex backgrounds and dense small-target conditions. For the occurrence risk discrimination task, a risk accuracy of $0.887$ is obtained, representing an improvement of approximately $4.5$ percentage points compared with the simple multimodal feature concatenation method. Cross-crop, cross-site, and cross-year generalization experiments further show that risk accuracy remains above $0.84$ with stable recognition performance under significant distribution shifts. Ablation studies verify the synergistic contributions of the proposed core modules to overall performance improvement. The results indicate that the proposed framework enables the transition from single recognition to risk-driven plant protection decision-making, providing a technically viable pathway for pest diagnosis and control strategy optimization in fruit and vegetable horticulture. Full article

Growing interest in environmentally compatible stored-product pest control has highlighted diatomaceous earth (DE) and 1,8-cineole as promising agents, both alone and in combination. Their different modes of action, together with the limitations associated with higher-dose single applications, support evaluating their combined use at lower doses. This study was conducted to compare the effects of DE and 1,8-cineole, applied alone and in combination, on the larval, pupal, and adult stages of Tenebrio molitor. Five different concentrations were tested for each substance (DE at 25, 50, 100, 250, and 500 ppm, and 1,8-cineole at 2.5, 5, 10, 15, and 20 ppm), and four DE + 1,8-cineole combinations were evaluated within the same experimental system. Mortality was monitored over time, LC₅₀ values were calculated by probit analysis, and larval output observed after adult treatments was also evaluated. The findings indicated that the biological response was associated with developmental stage. The lowest LC₅₀ for DE was recorded in larvae at 86.11 ppm on day 3, whereas for 1,8-cineole the lowest LC₅₀ was recorded in adults at 94.83 ppm on day 3. Combined treatments generally tended to produce faster and stronger mortality; in particular, the DE250 + CIN20 treatment reached 100% mortality in larvae and adults and 93.33% mortality in pupae by day 7. In addition, larval output decreased in the single-treatment groups, the proportion of dead larvae among the observed larvae increased to 96–100%, and no larval output was detected in the combination groups. Combinations of DE and 1,8-cineole tended to produce more pronounced mortality responses than the single treatments, particularly in the larval and adult stages. The present findings indicate that combining DE with 1,8-cineole may provide a promising stage-specific strategy for improving the control of T. molitor under laboratory conditions. Full article

The montane water vole, Arvicola scherman, is a fossorial rodent that lives underground in grasslands, pastures and meadows in the mountain ranges of southwestern and central Europe. It feeds mainly on grasses, roots, and bulbs, causing considerable economic damage to agriculture. Consequently, it is recognised as one of the most important pest vole species in European agroecosystems. The dynamics of these pest populations may be affected by interactions with their parasites. For this reason, an helminthoecological study was carried out in Asturias (NW Spain), analysing a total of 815 montane water voles, 464 (56.9%) of which were parasitised by at least one of the six helminth species detected: Hydatigera taeniaeformis s.l. larvae (9%), Aonchotheca wioletti (0.1%), Eucoleus bacillatus (0.4%), Trichuris arvicolae (7%), Carolinensis minutus (30%) and Syphacia nigeriana (12%). The helminth community found was compared with that reported from A. scherman analysed in other locations of the Iberian Peninsula. This study also analyses the influence of intrinsic and extrinsic factors on the prevalence and abundance of the helminth component species, with host age and body condition being the most influential determinants. H. taeniaeformis s.l. and T. arvicolae are postulated as potential regulators of the analysed population, a pest in crops from NW Spain. Full article

Varroa destructor (Bee mite) and Deformed Wing Virus are primary causes of honeybee colony collapse. This study developed an automated AI-based vision inspection system for detecting bee mites and deformed bees using the YOLO algorithm. The system integrates an RGB camera, a beecomb rotation motor, and an image transmission module to enable automated dual-sided image acquisition of the beecomb. The image characteristics of normal bees, bee mites, and deformed bees were analyzed, and YOLO-based object detection models were developed to classify them. Six YOLO models—based on YOLOv8 and YOLOv11 architectures across three model sizes (nano, small, and large)—were evaluated on 405 test images (6441 objects). The proposed system reduced the inspection time from 240 s required for manual method to 20 s per beecomb, achieving 12-fold efficiency improvement. Comparative analysis showed model-task specialization: YOLOv8l excelled in detecting small bee mites (F1: 92.5%, mAP[0.5]: 92.1%), while YOLOv11s achieved the highest performance for morphologically diverse deformed bees (F1: 95.1%). Error analysis indicated that detection performance was influenced by morphological characteristics. Deformed bee detection errors correlated with overlap in wing-to-body ratio: DB Type II exhibited 18.6% miss rate, while DB Type III achieved perfect detection. In bee mite detection, a sensitivity–specificity trade-off was observed: YOLOv11l had the lowest false negatives (2.5%) but highest false positives, while YOLOv8l demonstrated superior discrimination. These results demonstrate the practical potential of the proposed system for field deployment in apiaries, supporting early pest diagnosis and improved colony health management. The model-task specialization framework provides guidance for architecture selection based on object characteristics. Future work will focus on multi-location validation and real-time monitoring integration. Full article

Mealybugs (Hemiptera: Pseudococcidae) are one of the prevalent pests infesting wine grapes in the eastern United States. Their close association with ants (Hymenoptera: Formicidae) provides them with protection against natural enemies. Although sugar-based dispensers have been proposed as a strategy to disrupt this trophobiotic interaction, their field performance and indirect effects on mealybug infestation remain poorly understood. This study addresses this gap by identifying mealybug species present in Virginia vineyards, characterizing dominant ant genera associated with mealybugs, and evaluating the impact of sugar dispensers (with and without insecticide) on ant activity, mealybug density, and fruit cluster infestation. Field trials were conducted in two commercial vineyards in Virginia, USA, both with a history of mealybug infestations. Sampling plots with or without sugar dispensers were compared to assess differences in mealybug and ant population densities and fruit cluster infestation levels. Two mealybug species, Pseudococcus maritimus (Ehrhorn) and Ferrisia gilli Gullan, were detected at both sites. Some dominant ant genera, including Tetramorium Mayr, Lasius Fabricius, Solenopsis molesta (Say), Crematogaster Lund, and Pheidole Westwood, were found in close association with mealybugs. Ant activity remained low in untreated plots, whereas insecticide-treated dispensers initially attracted high ant numbers, which declined over time. Fruit cluster infestation was highest in plots lacking dispensers, indicating that dispenser deployment reduced mealybug impact. These findings demonstrate that sugar dispensers, particularly those containing insecticide, can suppress ant activity and reduce mealybug-related fruit damage, offering a practical non-disruptive tool for integrated pest management in small- and medium-sized vineyards. Full article

Artificial intelligence (AI)-assisted drone technology in agriculture has transformed productivity and pest control techniques, resulting in novel solutions to modern farming challenges. Drones utilizing sensors, cameras, and AI algorithms can precisely monitor crop health, soil conditions, and insect infestations. Using AI-assisted drones for precision irrigation and yield predictions further improves resource allocation, promotes sustainability, and reduces operating costs. This review examines recent advancements in AI and unmanned aerial vehicles (UAVs) in precision agriculture. Key trends include AI-driven crop disease detection, UAV-enabled multispectral imaging, precision pest management, smart tractors, variable-rate fertilization, and integration with IoT-based decision support systems. This study synthesizes current research to identify technological progress, implementation challenges, scalability barriers, and opportunities for sustainable agricultural transformation. This review of peer-reviewed studies published between 2013 and 2025 uses major scientific databases and predefined inclusion and exclusion criteria covering crop monitoring, precision input application, integrated pest management (IPM), and livestock (especially cattle) monitoring. We describe the platform and payload trade-offs that govern coverage, endurance, and spray quality; the dominant analytics trends, from classical machine learning to deep learning and embedded/edge inference; and the emerging shift from monitoring-only UAV use toward closed-loop decision-making (detection–prediction–intervention). Across the literature, the strongest opportunities lie in robust field validation, multi-modal data fusion (UAV + ground sensors + farm records), and interoperable standards that enable actionable IPM decisions. Key gaps include limited cross-site generalization, scarce reporting of economic indicators (ROI, payback period, and adoption rate), and regulatory and safety barriers for routine autonomous operations. Finally, we present some case studies to emphasize the feasibility and highlight future research directions of AI-assisted drone technology. Through this review, we aim to demonstrate technological advancements, challenges, and future opportunities in AI-assisted drone applications, ultimately advocating for more sustainable and cost-effective farming practices. Full article

Parasitoid wasps play a fundamental role in the biological control of pests. However, their morphological identification may be limited due to their small size and the high morphological similarity between species. Our objective was to identify specific genomic variants of the target species Palmistichus elaeisis Delvare & LaSalle, 1993, Tetrastichus howardi (Olliff, 1893), Trichospilus diatraeae Cherian & Margabandhu, 1942, and Trichogramma pretiosum Riley, 1879, (Hymenoptera: Chalcidoidea) by whole-genomic sequencing. Parasitoids were collected from their hosts and established in the laboratory after adult emergence. A sample of each parasitoid was sent to the Departamento de Ciências Biológicas at Universidade Federal do Espírito Santo (UFES) and “Oscar Monte” Entomophagous Insect Collection for morphological identification. Subsequently, samples composed of 20 individuals were preserved in absolute ethanol for DNA extraction. The DNA was extracted, quantified and sequenced on the Illumina Novaseq 6000 platform. Bioinformatic tools were used for quality control, detection of specific genomic variants, principal component analysis (PCA), and support vector machine (SVM). Genomic sequencing generated high-quality data for the analyzed parasitoids, allowing the identification of four specific variants for P. elaeisis, two for Te. howardi, four for Ts. diatraeae and five for Tg. pretiosum. These results provide a precise molecular tool for distinguishing parasitoids used in biological control programs. Full article

The significant differences in insects trapped by pest detection lamps lead to low classification accuracy of existing models for rice pests. To address this issue, this paper proposes a small pest target detection and classification model (ViT-YOLOv5p) by integrating the YOLO backbone and Transformer module. First, the number of training samples is expanded through data augmentation during model training. Furthermore, appropriate noise data are introduced to enhance the robustness and generalization ability of the model. Before detection and classification, image cutting and stitching strategies are adopted to improve the detection accuracy of small objects. The bounding box of the pest is determined by the YOLO backbone, and the corresponding region is fed into the Transformer model to obtain the classification result. Finally, YOLOv5, Faster R-CNN, YOLOv4, and the proposed ViT-YOLOv5p are trained on the same dataset, with average detection time (ADT) and classification accuracy employed as evaluative metrics. The results show that ViT-YOLOv5p achieves the highest classification accuracy of 91.89% with an ADT of 50.41 ms. Compared with the commonly used Faster R-CNN, YOLOv5, and YOLOv4 models, the accuracy is improved by 1.50%, 8.71%, and 9.74%, respectively. This study provides a reference for agricultural pest detection, automatic insect classification systems, and deep learning-based detection of small agricultural targets. Full article

The Coffee Berry Borer is the most destructive pest affecting global production of Coffea arabica. Early detection of pest-induced fruit damage remains challenging due to the small size of infestation symptoms and the dense clustering of coffee berries under complex field conditions. This study evaluates optimized object detection architectures designed to improve the balance between detection accuracy and computational efficiency. Three baselines were established: YOLOv8n (M0), YOLOv11n (M1), and YOLOv26n (M2). Seven architectural variants (M3–M9) were then developed by integrating FasterNet, SimSPPF, and EMA. Experimental results showed that M0 achieved the highest detection accuracy (mAP@0.5 = 0.9534 and 6.09 GFLOPs), whereas model M6, combining FasterNet and SimSPPF, provided the best accuracy–efficiency trade off with mAP@0.5 = 0.9446 and 5.12 GFLOPs. Pareto analysis confirmed M6 as the optimal configuration. Finally, in situ validation across 25 points achieved a mean F1-score of 0.7255 (SD = 0.0504) for infected berries despite cast shadows, proving its readiness for real-time agricultural deployment. Full article

Insect sex pheromone receptors (PRs) are crucial for regulating mating and reproduction. In the insect olfactory perception pathway, the pheromone-binding protein (PBP) facilitates the efficient translocation of sex pheromones, enabling them to bind to PRs. PRs convert chemical signals into electrical signals, which are transmitted to the insect central nervous system to ultimately regulate reproductive behaviors. Thus, conducting functional analysis of PRs not only clarifies the molecular mechanism underlying insect mating via sex pheromone recognition and reveals the intrinsic regulatory link between sex pheromone detection and mating behavior but also provides theoretical support for the scientific understanding of the insect olfactory system. Additionally, this research lays a core theoretical foundation for the development of green pest control technologies in agriculture and forestry. This paper systematically reviews the research methods, technical principles, and advantages and disadvantages of techniques used to study insect PR genes. It summarizes representative identified PRs and their corresponding research strategies, aiming to provide a reference for future investigations into insect chemical communication and for the advancement of pest control practices. Full article

Araucaria araucana (Molina) K. Koch, an endemic conifer of Chile and Argentina, has been severely impacted in recent years by Araucaria Leaf Damage (ALD). Previous research has established that volatile organic compounds (VOCs) released by healthy (H) and leaf-damaged (LD) Araucaria araucana branches modulate the behavior of Sinophloeus porteri. Specifically, myrcene, the most abundant compound in healthy branches, acts as a repellent to this insect, whereas hibaene, found in high concentrations in leaf-damaged tissue, acts as an attractant. This study compared the chemical profiles of healthy and leaf-damaged branches across two distinct geographic areas: Nahuelbuta (PNN) and Villarrica (PNV) National Parks. Following VOC capture using Porapak Q and subsequent GC-MS analysis, 31 compounds were detected and 29 were identified. The results indicate that hibaene was consistently detected across health categories, whereas camphor was particularly abundant in leaf-damaged trees from PNV. Overall, the data suggest that tree health status is associated with marked changes in VOC profiles, although the present design does not allow constitutive and induced responses to be fully disentangled. Consequently, monitoring these volatile emissions represents a strategic tool for the early detection and mitigation of damage caused by pests and diseases in these forest ecosystems. Full article